INDEX

Explanations

mentions of law enforcement related terms

oai_token-act-pair · gpt-3.5-turbo

terms related to law enforcement and legal matters

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

auga

-0.95

yip

-0.88

ngth

-0.83

voy

-0.81

selage

-0.77

iliary

-0.76

ako

-0.74

hiba

-0.74

uchi

-0.73

uras

-0.73

POSITIVE LOGITS

enforcement

0.87

 ACTIONS

0.83

 regulating

0.79

 affirmative

0.70

 precedent

0.69

 enacted

0.69

ASED

0.68

CTR

0.68

 jurisdiction

0.68

 authorizing

0.66

Activations Density 0.313%

mentions of law enforcement related terms

terms related to law enforcement and legal matters

No Comments

No Known Activations